Big Data Analytics

What’s in your food? A new technology platform shows early signs of promise

Share this post:

When you buy food from the supermarket or order at a restaurant, an apple can clearly be identified as an apple. But how can you be sure of the contents of a spice mix, ground beef, or fish cakes? Unintentional contamination and intentional fraud can occur in the food supply chain. Food authentication is emerging as an important field, and at IBM Research we are applying a multidisciplinary approach in collaboration with industry and academia to address this global challenge.

As food supply chains become increasingly global and complex, more sophisticated approaches to ensuring safe food are needed. The Consortium for Sequencing the Food Supply Chain aims to explore the application of genomics and big data to food safety in order to generate new insights and understanding of the total supply chain, ultimately moving towards prediction and prevention of food safety incidents. Consortium founders IBM Research and Mars Incorporated, together with member Bio-Rad Laboratories and consulting professor Dr. Bart Weimer of the UC Davis School of Veterinary Medicine, have been testing a new way to authenticate the composition of raw materials. Through the application of metagenomics, analytics and cloud technology we are generating new insights and understanding of food supply chains.

As described in our co-authored research paper Food authentication from shotgun sequencing reads with an application on high protein powders, published today in the Nature Partner Journal Science of Food, the consortium has created a new pipeline for food component identification that can simultaneously detect multiple expected and unexpected components. In a world where global food supply chains are increasingly complex, this research showed that such a pipeline has potential for reliable ingredient authentication.

Food authentication is becoming increasingly important, as contamination and fraud can occur at any point within a supply chain. IBM researchers are collaborating with industry and academia to use metagenomics, analytics and cloud to build new ways to authenticate the composition of raw materials.

Food authentication is becoming increasingly important, as contamination and fraud can occur at any point within a supply chain. IBM researchers are collaborating with industry and academia to use metagenomics, analytics and cloud to build new ways to authenticate the composition of raw materials.

How does the pipeline work?

This new approach involves evaluating DNA and RNA sequencing data from food against a database of thousands of plant and animal genomes. In this proof-of-concept work, a food authentication pipeline was initially developed using simulated and experimental datasets, and then applied to 31 high protein powder (HPP) samples.

Analyzing the HPP samples was exciting as this was the first time that food ingredient sequencing at this scale had been done, and we did not know what to expect from applying the pipeline. This research indicated traces of other ingredients introduced — possibly during ingredient transport or processing — and the effectiveness of sequencing in verifying authenticity.

More work and data is needed and ongoing efforts within the Consortium for Sequencing the Food Supply Chain include assessing microbiomes for potential food safety applications. Together, we are building new capabilities through advancing science and technology to better ensure the safety, quality and authenticity of foods and their ingredients.

Reference

Haiminen, N., Edlund, S., Chambliss, D. et al. Food authentication from shotgun sequencing reads with an application on high protein powders. npj Sci Food 3, 24 (2019) doi:10.1038/s41538-019-0056-6

 

Research Staff Member, Computational Genomics

More Big Data Analytics stories

Meet Ari, the Smart Bike that Helps you Catch Green Lights

As more bikes take to the city streets than ever, researchers at RMIT have designed Ari, a smart e-bike that could help riders cruise the ‘green wave’.

Continue reading

Overcoming Challenges in Building Enterprise AI Assistants

A team of researchers from IBM Research AI and AI Horizons Network-partner the University of Michigan published the papers “A Large-Scale Corpus for Conversation Disentanglement” and “Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use” at ACL 2019. This work address two main challenges in building enterprise AI assistants.

Continue reading

Four Papers Advance Computational Argumentation in IBM’s Project Debater

The latest work on computational argumentation from the IBM Project Debater research team group is being presented at the ACL 2019 conference. Three papers will be presented at the main conference and one more paper will be presented in the co-located Argument Mining Workshop.

Continue reading